AI Threat AlertPatchPoison: Poisoning Multi-View Datasets to Degrade 3D Reconstruction
exploited to reconstruct detailed 3D models of scenes or objects without the owner's consent. We present PatchPoison, a lightweight dataset-poisoning method that prevents unauthorized 3D reconstruction. Unlike global
Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses
based, and hybrid perturbations in both poisoning and evasion scenarios. Our extensive analysis reveals multiple findings, among which three are particularly noteworthy: 1) models have inherent robustness trade-offs between
On the Vulnerability of Deep Automatic Modulation Classifiers to Explainable Backdoor Threats
breaching multiple DL-based AMC models. The attack achieves high success rates for a wide range of SNR values and a small poisoning ratio
RAG Security and Privacy: Formalizing the Threat Model and Attack Surface
knowledge, the first formal threat model for retrieval-RAG systems. We introduce a structured taxonomy of adversary types based on their access to model components and data, and we formally
EVOMAL: Self-Poisoning in Self-Evolving Coding Agents
skill to the library. Across six models on 153 tool-relevant SWE-bench Verified tasks, ASPR ranges from 20.3% to 41.8%, and the poisoned libraries hold 4.9 to 9.0 times
Statistical Adversaries: Natural Backdoor-like Features in Vision Datasets
that these signals directly and predictably alter model predictions. These statistical adversaries are more targeted than generic corruptions and transfer across different model architectures. This suggests that some vulnerabilities
PEEL: A Poisoning-Exposing Encoding Theoretical Framework for Local Differential Privacy
widely adopted privacy-protection model in the Internet of Things (IoT) due to its lightweight, decentralized, and scalable nature. However, it is vulnerable to poisoning attacks, and existing defenses either
Stealthy Backdoor Attacks against LLMs Based on Natural Style Triggers
attack framework and pipeline. BadStyle leverages an LLM as a poisoned sample generator to construct natural and stealthy poisoned samples that carry imperceptible style-level triggers while preserving semantics
Revisiting Backdoor Threat in Federated Instruction Tuning from a Signal Aggregation Perspective
vulnerabilities from low-concentration poisoned data distributed across the datasets of benign clients.} This scenario is increasingly common in federated instruction tuning for language models, which often rely on unverified
Benchmarking Quantum Machine Learning for Power-System Attack Detection: Evaluation Choices Decide the Outcome Before the Models Do
classifiers against six tuned classical models on public power-system attack data (Mississippi State/ORNL), across white-box, transfer, decision-based black-box, and poisoning attacks. Our headline finding is methodological
Safety, Security, and Cognitive Risks in World Models
risks. Adversaries can corrupt training data, poison latent representations, and exploit compounding rollout errors to cause catastrophic failures in safety-critical deployments. World model-equipped agents are more capable
OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences
Memory-augmented large language model (LLM) agents use iterative reflection and self-evolution to solve complex tasks, but these mechanisms introduce security risks. Existing agentic memory attacks require privileged access
GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs
Recent work integrates Large Language Models (LLMs) with Graph Neural Networks (GNNs) to jointly model semantics and structure, resulting in more general and expressive models that achieve state
Adversarial Benchmarks and BenchDoor Attacks: Exploiting Benchmark Incentives for Backdoor Attacks
guideposts for model development and spur the creation of training datasets intended to improve benchmark scores. We introduce BenchDoor, a family of data poisoning attacks that exploits this incentive. Beyond
Rapid Poison: Practical Poisoning Attacks Against the Rapid Response Framework
injection can infiltrate this pipeline to deliver poisoned samples into the classifier's training set, enabling two attack objectives: (I) targeted poisoning attacks that create false positives on harmless samples
Reasoning-Style Poisoning of LLM Agents via Stealthy Style Transfer: Process-Level Attacks and Runtime Monitoring in RSV Space
Large Language Model (LLM) agents relying on external retrieval are increasingly deployed in high-stakes environments. While existing adversarial attacks primarily focus on content falsification or instruction injection, we identify
Are AI-assisted Development Tools Immune to Prompt Injection?
development tools built on the Model Context Protocol (MCP). However, their convenience comes with security risks, especially prompt-injection attacks delivered via tool-poisoning vectors. While prior research has studied
Architecting the Secure AI-SOC: A Neurosymbolic Framework for Pipeline Integrity and Threat Mitigation
integration of Large Language Models (LLMs) into Security Operations Centers (SOCs) streamlines threat intelligence but introduces critical vulnerabilities, notably indirect prompt injection via log poisoning. Adversaries exploit this vector
Rethinking Penetration Testing for AI-Enabled Systems: From Resource Compromise to Behavioral Objective Violation
under an explicit threat model. This definition preserves conventional penetration testing while extending it to adversarial pathways such as prompt injection, indirect prompt injection, data poisoning, sensor manipulation, retrieval poisoning
Rethinking the Transferable Adversarial Attacks and Robust Defense in Federated Learning
open opportunities for different adversaries, such as poisoning attacks, Byzantine attacks, and adversarial example attacks. Yet, recent research has disclosed that existing poisoning attacks and Byzantine attacks can not achieve